We consider the problem of recovering an unknown matching between a set of $n$ randomly placed points in $\mathbb{R}^d$ and random perturbations of these points. This can be seen as a model for particle tracking and more generally, entity resolution. We use matchings in random geometric graphs to derive minimax lower bounds for this problem that hold under great generality. Using these results we show that for a fixed $d$, as long as the noise distribution has finite $d$-th moment, and both initial positions and noise have bounded continuous densities, the minimax rate for the problem scales as $Θ(n^2σ^d \wedge n)$. Under the stronger assumptions that the tail of the noise is sub-Gaussian, we show that the order of the number of mistakes made by an estimator that minimizes the sum of squared Euclidean distances is minimax optimal when $d$ is fixed and is optimal up to $n^{o(1)}$ factors when $d = o(\log n)$. In the high-dimensional regime we consider a setup where both initial positions and perturbations have independent sub-Gaussian coordinates. In this setup we give sufficient conditions under which the same estimator makes no mistakes with high probability. We prove an analogous result for an adapted version of this estimator that incorporates information on the covariance matrix of the perturbations.
The statistical threshold for planted matchings and spanning trees
McGill University（麦吉尔大学）；University of British Columbia（不列颠哥伦比亚大学）；Pompeu Fabra University（庞培法布拉大学）；ICREA（加泰罗尼亚高级研究院）；Barcelona Graduate School of Economics（巴塞罗那经济研究生院）；Northwestern University（西北大学）；Stanford University（斯坦福大学）
